HIGH-PRECISION SHORT-TERM PREDICTION METHOD OF WIND SPEED AND POWER FOR OFFSHORE WIND FARM BASED ON MIGRATION LEARNING WITH CNN-LSTM

Yu Biao; Wang Zhuoheng; Qi Xiao; Sun Shanxun; Zang Xinghai; Sheng Faming

doi:10.19912/j.0254-0096.tynxb.2024-2060

PDF(6109 KB)

Acta Energiae Solaris Sinica ›› 2026, Vol. 47 ›› Issue (4) : 222-230. DOI: 10.19912/j.0254-0096.tynxb.2024-2060

HIGH-PRECISION SHORT-TERM PREDICTION METHOD OF WIND SPEED AND POWER FOR OFFSHORE WIND FARM BASED ON MIGRATION LEARNING WITH CNN-LSTM

Yu Biao¹, Wang Zhuoheng², Qi Xiao², Sun Shanxun², Zang Xinghai¹, Sheng Faming¹

Author information +

History +

Abstract

In offshore wind power scenarios, short-term prediction of wind speed and power faces many challenges. Conventional long short-term memory neural networks （LSTM） struggle to accurately predict wind speed and power in far-reaching offshore wind farms. To address this challenge, this study deploys a Doppler lidar in an offshore wind farm in Guangdong, and collects measured wind speed data. To address the reasons for the insufficient prediction accuracy, this paper proposes a convolutional neural network-long short-term memory （CNN-LSTM） prediction model based on migration learning. Migration learning can accelerate new task learning and improve model performance by utilizing knowledge from similar tasks; CNN is good at extracting spatial features of radar data; and LSTM is good at capturing long-term dependencies of time series. The combination of these features makes the method proposed in this paper perform well in improving wind speed prediction and power prediction for offshore wind power. The experimental results show that compared with the original radar data and the conventional LSTM model, the new method significantly reduces the error in predicting the offshore wind speed and wind power, and the prediction accuracy is better improved.

Key words

offshore wind farm / machine learning / wind power / wind forecasting / CNN-LSTM network / Doppler lidar

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Yu Biao, Wang Zhuoheng, Qi Xiao, Sun Shanxun, Zang Xinghai, Sheng Faming. HIGH-PRECISION SHORT-TERM PREDICTION METHOD OF WIND SPEED AND POWER FOR OFFSHORE WIND FARM BASED ON MIGRATION LEARNING WITH CNN-LSTM[J]. Acta Energiae Solaris Sinica. 2026, 47(4): 222-230 https://doi.org/10.19912/j.0254-0096.tynxb.2024-2060

References

[1] 中国可再生能源学会风能专业委员会, 全球风能理事会. 海上风电回顾与展望2025[EB/OL].[2025-06-23]. https://wind.in-en.com/html/wind-2460254.shtml.
Chinese Wind Energy Association, Global Wind Energy Council. Offshore wind power review and prospects2025[EB/OL].[2025-06-23]. https://wind.in-en.com/html/wind-2460254.shtml.
[2] 刘星斗. 基于WRF与深度神经网络的风电功率预测[D]. 济南: 山东大学, 2022.
LIU X D.Wind power prediction based on WRF and deep neural network[D]. Ji’nan: Shandong University, 2022.
[3] LIU X L, LIN Z, FENG Z M.Short-term offshore wind speed forecast by seasonal ARIMA-A comparison against GRU and LSTM[J]. Energy, 2021, 227: 120492.
[4] 江国乾, 徐向东, 白佳荣, 等. 基于多粒度时间卷积网络的超短期风功率预测[J]. 太阳能学报, 2024, 45(5): 104-111.
JIANG G Q, XU X D, BAI J R, et al.Ultra-short-term wind power prediction based on multi-granularity temporal convolution network[J]. Acta energiae solaris sinica, 2024, 45(5): 104-111.
[5] 张群, 唐振浩, 王恭, 等. 基于长短时记忆网络的超短期风功率预测模型[J]. 太阳能学报, 2021, 42(10): 275-281.
ZHANG Q, TANG Z H, WANG G, et al.Ultra-short-term wind power prediction model based on long and short term memory network[J]. Acta energiae solaris sinica, 2021, 42(10): 275-281.
[6] 任东方, 马家庆, 何志琴, 等. 基于AVMD-CNN-GRU-Attention的超短期风功率预测研究[J]. 太阳能学报, 2024, 45(6): 436-443.
REN D F, MA J Q, HE Z Q, et al.Research on ultra-short-term wind power forecast based on AVMD-CNN-GRU-Attention[J]. Acta energiae solaris sinica, 2024, 45(6): 436-443.
[7] KHODAYAR M, WANG J H.Spatio-temporal graph deep neural network for short-term wind speed forecasting[J]. IEEE transactions on sustainable energy, 2019, 10(2): 670-681.
[8] 蒋建东, 孙书凯, 董存, 等. 风电中长期电量预测研究现状[J]. 高电压技术, 2022, 48(2): 409-419.
JIANG J D, SUN S K, DONG C, et al.Research status of mid-long term wind power generation forecasting[J]. High voltage engineering, 2022, 48(2): 409-419.
[9] LUO X, ZHANG D X, ZHU X.Deep learning based forecasting of photovoltaic power generation by incorporating domain knowledge[J]. Energy, 2021, 225: 120240.
[10] 王世明, 张少童, 娄嘉奕. 基于CNN-LSTM-ARIMA的超短期风速预测[J]. 新能源进展, 2024, 12(6): 688-695.
WANG S M, ZHANG S T, LOU J Y.Ultra-short-term wind speed forecasting based on CNN-LSTM-ARIMA[J]. Advances in new and renewable energy, 2024, 12(6): 688-695.
[11] REN J, YU Z P, GAO G L, et al.A CNN-LSTM-LightGBM based short-term wind power prediction method based on attention mechanism[J]. Energy reports, 2022, 8: 437-443.
[12] 唐清苇, 向月, 代佳琨, 等. 基于CNN-LSTM的风电场发电功率迁移预测方法[J]. 工程科学与技术, 2024, 56(2): 91-99.
TANG Q W, XIANG Y, DAI J K, et al.Wind farm power transfer forecasting method based on CNN-LSTM[J]. Advanced engineering sciences, 2024, 56(2): 91-99.
[13] 黄贤明, 郝雨辰, 霍雪松, 等. 基于时空混合注意力机制的超短时风电功率预测方法[J]. 现代电力, 2025, 42(5): 928-936.
HUANG X M, HAO Y C, HUO X S, et al.An ultra-short term wind power prediction method based on spatio-temporal hybrid attention mechanism[J]. Modern electric power, 2025, 42(5): 928-936.
[14] WU Q Y, GUAN F, LYU C, et al.Ultra-short-term multi-step wind power forecasting based on CNN-LSTM[J]. IET renewable power generation, 2021, 15(5): 1019-1029.
[15] 廉文超, 宋小全, 郝朝阳, 等. 双向长短期记忆网络在激光雷达风廓线预测的应用[J]. 光学学报, 2024, 44(24): 58-67.
LIAN W C, SONG X Q, HAO Z Y, et al.Application of bidirectional long short-term memory network in Doppler lidar wind profile prediction[J]. Acta optica sinica, 2024, 44(24): 58-67.
[16] LI N H, DYER-HAWES Q, ROMANIC D, et al. Investigation of coastal winds and turbulence characteristics using Doppler lidar[J]. Journal of geophysical research: atmospheres, 2024, 129(19): e2024JD041429.
[17] SALCEDO-BOSCH A, GUTIERREZ-ANTUNANO M A, TIANA-ALSINA J, et al. Floating Doppler wind lidar measurement of wind turbulence: a cluster analysis[C]//IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium. Waikoloa, HI, USA, 2021: 6077-6080.
[18] VAN DOOREN M F, TRABUCCHI D, KÜHN M. A methodology for the reconstruction of 2D horizontal wind fields of wind turbine wakes based on dual-Doppler lidar measurements[J]. Remote sensing, 2016, 8(10): 809.
[19] LU J, BEHBOOD V, HAO P, et al.Transfer learning using computational intelligence: a survey[J]. Knowledge-based systems, 2015, 80: 14-23.
[20] 王晓霞, 艾兴成, 王涛. 基于实例迁移学习的小样本光伏功率短期预测[J]. 太阳能学报, 2024, 45(6): 325-333.
WANG X X, AI X C, WANG T.Few-shot photovoltaic power short-term forecasting based on instance transfer learning[J]. Acta energiae solaris sinica, 2024, 45(6): 325-333.
[21] 刘明浩, 韩晓明, 何晨. 基于迁移学习训练的BiLSTM锂电池剩余使用寿命预测[J/OL]. 控制工程, 2024: 1-9. (2024-06-27). https://link.cnki.net/doi/10.14107/j.cnki.kzgc.20240140.
LIU M H, HAN X M, HE C. Prediction of remaining service life of BiLSTM lithium battery based on transfer learning training[J/OL]. Control engineering of China, 2024: 1-9. (2024-06-27). https://link.cnki.net/doi/10.14107/j.cnki.kzgc.20240140.
[22] 程明, 翟金星, 马骏, 等. 基于迁移学习的CNN-GRU短期电力负荷预测方法[J]. 武汉大学学报(工学版), 2024, 57(6): 812-820.
CHENG M, ZHAI J X, MA J, et al.Transfer learning based CNN-GRU short-term power load forecasting method[J]. Engineering Journal of Wuhan University, 2024, 57(6): 812-820.
[23] CHEN X H, YANG R, XUE Y H, et al.Deep transfer learning for bearing fault diagnosis: a systematic review since 2016[J]. IEEE transactions on instrumentation and measurement, 2023, 72: 3508221.
[24] LI J P, HUANG R Y, HE G L, et al.A two-stage transfer adversarial network for intelligent fault diagnosis of rotating machinery with multiple new faults[J]. IEEE/ASME transactions on mechatronics, 2021, 26(3): 1591-1601.
[25] D’INCECCO M, SQUARTINI S, ZHONG M J. Transfer learning for non-intrusive load monitoring[J]. IEEE transactions on smart grid, 2020, 11(2): 1419-1429.
[26] 马兆荣, 刘晋超, 元国凯. 珠海桂山海上风电场风电机组基础设计[J]. 南方能源建设, 2015, 2(3): 72-75.
MA Z R, LIU J C, YUAN G K.Design of wind turbine supporting structure in Zhuhai Guishan offshore wind farm[J]. Energy construction, 2015, 2(3): 72-75.
[27] 杨伟鹏. 海上波浪能与风能互补发电平台的控制系统研究与设计[D]. 北京: 华北电力大学, 2015.
YANG W P.Research and design of control system based on wave and wind energy complementary generation platform[D]. Beijing: North China Electric Power University, 2015.
[28] 吴春雷. 基于中尺度数值气象模式的风电场参数化建模方法研究[D]. 杭州: 浙江大学, 2023.
WU C L.Research on the wind farm parameterization based on the mesoscale numerical weather prediction model[D]. Hangzhou: Zhejiang University, 2023.